CN114170798B - Message reminding system and method - Google Patents
Message reminding system and method Download PDFInfo
- Publication number
- CN114170798B CN114170798B CN202111466524.6A CN202111466524A CN114170798B CN 114170798 B CN114170798 B CN 114170798B CN 202111466524 A CN202111466524 A CN 202111466524A CN 114170798 B CN114170798 B CN 114170798B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- unit
- road
- abnormal traffic
- line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0967—Systems involving transmission of highway information, e.g. weather, speed limits
- G08G1/096708—Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention discloses a message reminding system and a message reminding method, and relates to the technical field of computers. The embodiment comprises the following steps: the device comprises a camera, an edge calculation processing unit and a vehicle-mounted unit; placing the on-board unit in the vehicle when the vehicle enters the current road; the camera is used for collecting image data on the current road and sending the collected image data to the edge calculation processing unit; the edge calculation processing unit is used for analyzing the image data and identifying whether the vehicles running on the current road have abnormal traffic behaviors; when the abnormal traffic behavior of the vehicle running on the current road is determined, a reminding message is generated and sent to a vehicle-mounted unit in the vehicle with the abnormal traffic behavior; the vehicle-mounted unit is used for outputting a reminding message to remind a driver of a vehicle with abnormal traffic behaviors. The embodiment provides the capability of detecting abnormal traffic behaviors for the vehicles without automatic driving or driving assisting capability, and reduces the risk of traffic accidents.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a message reminding system and method.
Background
With the development of computer vision technology and deep learning technology, the intelligent traffic system becomes the development direction of future traffic systems, and various traffic illegal behaviors and accidents can be reduced. Among them, the illegal lane change of vehicles is a common illegal action and causes of traffic accidents. Therefore, accurate and efficient violation detection on the vehicle line pressing has extremely important significance for standardizing driver behaviors and reducing accident rate. However, some vehicles do not have an intelligent driving system or a driving assistance function, and do not have a pressure line detection function. How to carry out line pressing detection and reminding on a vehicle without an intelligent driving system or an auxiliary driving function becomes a problem to be solved urgently.
Disclosure of Invention
In order to solve the technical problem or at least partially solve the technical problem, embodiments of the present invention provide a message reminding system and method.
In a first aspect, an embodiment of the present invention provides a message reminding system, where the system includes a camera, an edge calculation processing unit, and an on-board unit, where the on-board unit is placed in a vehicle when the vehicle enters a current road; the camera is used for collecting image data on the current road and sending the collected image data to the edge calculation processing unit; the edge calculation processing unit is used for analyzing the image data and identifying whether vehicles running on the current road have abnormal traffic behaviors or not; when the abnormal traffic behavior of the vehicle running on the current road is determined, generating a reminding message, and sending the reminding message to a vehicle-mounted unit in the vehicle with the abnormal traffic behavior; and the vehicle-mounted unit is used for outputting the reminding message after receiving the reminding message so as to remind the driver of the vehicle with abnormal traffic behaviors.
In an optional embodiment, the system further comprises a road side unit; the edge calculation processing unit is further configured to send the reminding message to the road side unit; and the road side unit is used for sending the received reminding message to an on-board unit in a vehicle with abnormal traffic behaviors.
In an optional embodiment, the edge calculation processing unit is further configured to analyze the image data through a pre-trained semantic segmentation model, and identify whether abnormal traffic behaviors exist in vehicles traveling on the current road.
In an optional embodiment, the edge calculation processing unit is further configured to:
analyzing the image data through the pre-trained semantic segmentation model, identifying a road line on the current road and judging whether the road line is shielded; determining coordinate information of the occluded road line in the case that it is determined that the road line is occluded; identifying a vehicle traveling on the current road, and determining profile information of the vehicle traveling on the current road; and determining whether the vehicle has abnormal traffic behaviors according to the contour information and the coordinate information of the shielded road route, wherein the abnormal traffic behaviors comprise continuous line pressing behaviors and/or continuous merging behaviors.
In an optional embodiment, the edge calculation processing unit is further configured to:
for each frame of image in the image data, segmenting the image into line anchor frames through the pre-trained semantic segmentation model;
and identifying whether each line anchor point in the line anchor frame is a lane line or not so as to identify a lane line on the image.
In an optional embodiment, the edge calculation processing unit is further configured to:
under the condition that the road line on the image is determined to be shielded, enlarging the receptive field of the pre-trained semantic segmentation model to determine the coordinate information of the shielded road line;
performing polynomial fitting according to the coordinate information of the shielded road line to obtain a fitted curve of the lane line;
displaying the shielded road line on the image according to the fitted curve of the lane line to obtain a complete road line;
smoothing the complete road line according to the front frame image and the rear frame image of the image;
determining whether the vehicle is pressed according to the contour information and the smoothed complete road line;
and tracking the vehicle under the condition of the vehicle line pressing, and determining whether the vehicle has abnormal traffic behaviors.
In an optional embodiment, the vehicle-mounted unit includes a voice broadcast unit, and the voice broadcast unit is configured to broadcast the reminder message.
In an optional embodiment, the system further comprises a binding unit, configured to record an association relationship between the on-board unit and the vehicle when the on-board unit is placed in the vehicle entering the current road, so as to bind the on-board unit and the vehicle;
the edge calculation processing unit is further configured to: under the condition that the abnormal traffic behavior of the vehicles running on the current road is determined, taking the vehicles with the abnormal traffic behavior as target vehicles, and determining target vehicle-mounted units bound with the target vehicles according to the incidence relation recorded by the binding units;
the roadside unit is further to: and sending the received reminding message to a target vehicle-mounted unit in the target vehicle.
In an optional embodiment, the binding unit is further configured to: recording the ID of the vehicle-mounted unit and the attribute information of the vehicle, and determining the association relationship between the vehicle-mounted unit and the vehicle so as to bind the vehicle-mounted unit and the vehicle;
the edge calculation processing unit is further configured to: inquiring a preset content library, and determining reminding content corresponding to the abnormal traffic behavior of the target vehicle; determining attribute information of the target vehicle; determining the ID of a target vehicle-mounted unit placed in the target vehicle according to the attribute information of the target vehicle and the incidence relation recorded by the binding unit; generating a reminding message according to the reminding content and the ID of the target vehicle-mounted unit in the target vehicle;
the roadside unit is further to: analyzing the reminding message, and determining the ID and the reminding content of the target vehicle-mounted unit in the target vehicle; and sending the reminding content to a target vehicle-mounted unit in the target vehicle according to the ID of the target vehicle-mounted unit in the target vehicle.
In a second aspect, an embodiment of the present invention provides a message reminding method, where the reminding method is applied to a message reminding system provided in any embodiment of the present invention; the method comprises the following steps:
acquiring image data on a current road through a camera, and sending the acquired image data to the edge calculation processing unit;
analyzing the image data through an edge computing processing unit, and identifying whether vehicles running on the current road have abnormal traffic behaviors; when the abnormal traffic behavior of the vehicle running on the current road is determined, generating a reminding message, and sending the reminding message to a vehicle-mounted unit in the vehicle with the abnormal traffic behavior;
and outputting the reminding message through a vehicle-mounted unit so as to remind a driver of the vehicle with the abnormal traffic behavior.
In an optional embodiment, the method further comprises: sending the reminding message to the road side unit through the edge calculation processing unit; and sending the received reminding message to an on-board unit in a vehicle with abnormal traffic behaviors through the road side unit.
In an optional embodiment, the method further comprises: and analyzing the image data through a pre-trained semantic segmentation model, and identifying whether the vehicles running on the current road have abnormal traffic behaviors.
In an optional embodiment, the method further comprises: analyzing the image data through the pre-trained semantic segmentation model, identifying a road route on the current road, and judging whether the road route is shielded; determining coordinate information of the occluded road line in the case that it is determined that the road line is occluded; identifying a vehicle traveling on the current road, and determining profile information of the vehicle traveling on the current road; and determining whether abnormal traffic behaviors exist in the vehicle or not according to the contour information and the coordinate information of the shielded road line, wherein the abnormal traffic behaviors comprise continuous line pressing behaviors and/or continuous line merging behaviors.
In an optional embodiment, the method further comprises: segmenting the image into line anchor frames through the pre-trained semantic segmentation model aiming at each frame of image in the image data; and identifying whether each line anchor point in the line anchor frame is a lane line or not so as to identify a lane route on the image.
In an optional embodiment, the method further comprises: determining coordinate information of the occluded road line by expanding a receptive field of the pre-trained semantic segmentation model if it is determined that the road line on the image is occluded; performing polynomial fitting according to the coordinate information of the shielded road line to obtain a fitted curve of the lane line; displaying the shielded road line on the image according to the fitted curve of the lane line to obtain a complete road line; smoothing the complete road line according to the front frame image and the rear frame image of the image; determining whether the vehicle is pressed according to the contour information and the smoothed complete road line; and tracking the vehicle under the condition of the vehicle line pressing, and determining whether the vehicle has abnormal traffic behaviors.
In an optional embodiment, the method further comprises: and broadcasting the reminding message through a voice broadcasting unit in the vehicle-mounted unit.
In an optional embodiment, the method further comprises: when a vehicle-mounted unit is placed in a vehicle entering the current road through a binding unit of the message reminding system, recording the association relationship between the vehicle-mounted unit and the vehicle so as to bind the vehicle-mounted unit and the vehicle; under the condition that the edge computing processing unit determines that abnormal traffic behaviors exist in vehicles running on the current road, the vehicles with the abnormal traffic behaviors are taken as target vehicles, and a target vehicle-mounted unit bound with the target vehicles is determined according to the incidence relation recorded by the binding unit; and sending the received reminding message to a target vehicle-mounted unit in the target vehicle through the road side unit.
In an optional embodiment, the method further comprises: recording the ID of the vehicle-mounted unit and the attribute information of the vehicle through the binding unit, and determining the association relationship between the vehicle-mounted unit and the vehicle so as to bind the vehicle-mounted unit and the vehicle; querying a preset content library through the edge computing processing unit, and determining reminding content corresponding to the abnormal traffic behavior of the target vehicle; determining attribute information of the target vehicle; determining the ID of a target vehicle-mounted unit placed in the target vehicle according to the attribute information of the target vehicle and the incidence relation recorded by the binding unit; generating a reminding message according to the reminding content and the ID of the target vehicle-mounted unit in the target vehicle; analyzing the reminding message through the road side unit, and determining the ID and the reminding content of a target vehicle-mounted unit in the target vehicle; and sending the reminding content to a target vehicle-mounted unit in the target vehicle according to the ID of the target vehicle-mounted unit in the target vehicle.
One or more of the above-described embodiments may have at least some or all of the following advantages:
according to the message reminding system provided by the embodiment of the invention, the camera is arranged at the high position of the current road, so that the system provided by the embodiment has the data acquisition capacity, the data (namely the image of the current road) acquired by the camera is identified through the edge calculation processing unit, whether abnormal traffic behaviors exist in the detection range is determined, if the abnormal traffic behaviors exist, the reminding message is generated and output, and therefore, the system provided by the embodiment has the abnormal traffic behavior detection capacity and the message transmission capacity; the vehicle-mounted unit is placed in a vehicle entering a current road (such as an expressway or an urban road), so that the vehicle has a technical means of receiving information, the capability of detecting abnormal traffic behaviors can be provided for the vehicle without automatic driving or driving assistance capability, the abnormal traffic behaviors of the vehicle can be accurately judged, early warning can be given to line pressing and lane changing of the vehicle, accidents such as rear-end collision and collision between the vehicle and surrounding vehicles can be prevented, the effect of safe driving assistance is achieved, the risk of traffic accidents is reduced, and safer driving guarantee is provided.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive labor.
FIG. 1 is a schematic structural diagram of a message alert system according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a message alert system according to another embodiment of the present invention;
FIG. 3 is a schematic diagram schematically illustrating an abnormal traffic behavior detection process of the message alert system according to the embodiment of the present invention;
FIG. 4 is a diagram that schematically illustrates a split-line anchor box in a message alert system, in accordance with an embodiment of the present invention;
FIG. 5 is a diagram schematically illustrating line anchor point identification in a message alert system according to an embodiment of the present invention;
fig. 6 schematically shows a structural diagram of a message reminding system according to still another embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Fig. 1 schematically shows a structural diagram of a message reminding system 100 according to an embodiment of the present invention. As shown in fig. 1, the message alert system 100 includes a camera 101, an edge calculation processing unit 102, and an in-vehicle unit.
The camera 101 is configured to collect image data on a current road, and send the collected image data to the edge calculation processing unit. The edge calculation processing unit 102 is configured to analyze the image data and identify whether a vehicle traveling on the current road has an abnormal traffic behavior; and when the abnormal traffic behavior of the vehicle running on the current road is determined, generating a reminding message, and sending the reminding message to the vehicle-mounted unit 103 in the vehicle with the abnormal traffic behavior. In an alternative embodiment, the edge calculation processing unit 102 may further send a warning message to an on-board unit in the associated vehicle, where the associated vehicle is a vehicle around the vehicle with abnormal traffic behavior. The vehicle-mounted unit 104 is configured to output the reminding message after receiving the reminding message, so as to remind a driver of the vehicle with the abnormal traffic behavior.
The camera 101 may be mounted higher up on the current road, for example on a road bar. The installation distance of the camera 101 passes through detection distance and adjustment, and the camera has no dead angle covering capability and can clearly shoot the lane line on the current road. The current road may be an expressway or an urban road, and the present invention is not limited thereto. The edge calculation processing unit 102 and the on-board unit 103 have communication capability and can perform data interaction. In an alternative embodiment, the edge calculation processing unit 102 may be integrated on the camera 101. The On Board Unit (OBU) 103 is a device that performs Communication using DSRC (Dedicated Short Range Communication) technology. When a vehicle enters a current road, the vehicle-mounted unit can be taken at an entrance of the current road and placed in the vehicle, so that the vehicle-mounted unit moves along with the vehicle, and the vehicle has message receiving capability.
According to the message reminding system provided by the embodiment of the invention, the camera is arranged at the high position of the current road, so that the system provided by the embodiment has data acquisition capacity, the data (namely the image of the current road) acquired by the camera is identified through the edge computing processing unit, whether abnormal traffic behaviors exist in the detection range is determined, and if the abnormal traffic behaviors exist, the reminding message is generated and output, so that the system provided by the embodiment has abnormal traffic behavior detection capacity and message transmission capacity; the vehicle-mounted unit is placed in a vehicle entering a current road (such as an expressway or an urban road), so that the vehicle has a technical means of receiving information, the capability of detecting abnormal traffic behaviors can be provided for the vehicle without automatic driving or driving assistance capability, the abnormal traffic behaviors of the vehicle can be accurately judged, early warning can be given to line pressing and lane changing of the vehicle, accidents such as rear-end collision and collision between the vehicle and surrounding vehicles can be prevented, the effect of safe driving assistance is achieved, the risk of traffic accidents is reduced, and safer driving guarantee is provided.
In an optional embodiment, the on-board unit comprises a voice broadcast unit. The voice broadcasting unit is used for broadcasting the reminding message.
Fig. 2 schematically shows a structural schematic diagram of a message reminding system 200 according to another embodiment of the present invention, and as shown in fig. 2, the message reminding system 200 includes a camera 201, an on-board unit 203 and a roadside unit 204 of an edge calculation processing unit 202.
The camera 201 is configured to collect image data on a current road, and send the collected image data to the edge calculation processing unit 202; the edge calculation processing unit 202 is configured to analyze the image data, and identify whether there is an abnormal traffic behavior in a vehicle traveling on the current road; and when determining that abnormal traffic behaviors exist in the vehicles running on the current road, sending a reminding message to the roadside unit 204. In this embodiment, the cameras 2011 may be installed at equal intervals on the road bar of the current road, and the installation distance of the camera 201 is adjusted through the detection distance and the angle, so that the camera has no dead angle coverage capability, can shoot a clear lane line, and is used for shooting the cars running on the current road in real time. The Edge Computing unit (Mobile Edge Computing) 202 detects lane lines on the image in real time by a lane line detection algorithm, and determines whether there is a case of continuous line pressing or continuous line doubling. The edge calculation processing unit 202 identifies a lane line on the current road through a pre-trained semantic segmentation model, then judges whether the lane line is blocked, judges whether the lane line is a vehicle line pressing line if the lane line is blocked, tracks the vehicle if the lane line is the vehicle line pressing line, determines whether the vehicle continuously presses the line or continuously merges the line, and pushes a reminding message to the roadside unit if the lane line is the vehicle line pressing line. The road side unit is used for sending the received reminding message to an on-board unit in a vehicle with abnormal traffic behaviors; or sending the received reminding message to vehicle-mounted units in vehicles around the vehicle with the abnormal traffic behavior. The pre-trained semantic segmentation model is obtained by carrying out massive training on an open data set or a self-collected data set, and the position of the lane line is presumed by the existing lane line pixels, other lane lines, road outlines and the driving directions of other vehicles and is trained to presume the position of the lane line.
Specifically, the edge calculation processing unit 202 is further configured to analyze the image data through a pre-trained semantic segmentation model, and identify whether there is an abnormal traffic behavior of a vehicle traveling on the current road.
Fig. 3 is a schematic diagram schematically showing the main steps of processing image data by the message alert system according to the embodiment of the present invention. As shown in fig. 3, the process of analyzing image data by the edge calculation processing unit 202 according to the embodiment of the present invention through the pre-trained semantic segmentation model includes:
step S301: identifying a road line on the current road and judging whether the road line is blocked;
step S302: under the condition that the road line is determined to be occluded, determining coordinate information of the occluded road line;
step S303: identifying a vehicle traveling on the current road, and determining profile information of the vehicle traveling on the current road;
step S304: and determining whether the vehicle has abnormal traffic behaviors according to the contour information and the coordinate information of the shielded road route, wherein the abnormal traffic behaviors comprise continuous line pressing behaviors and/or continuous merging behaviors.
Specifically, as shown in fig. 4-5, the embodiment of the present invention divides each frame of image captured by the camera 201 into line anchor frames (row anchors). Wherein the position and size of the line anchor box is predefined. After the image is divided into line anchor frames, it is identified whether each line anchor point (anchor box) in the line anchor frames is a lane line to identify a lane line on the image. The embodiment of the invention judges whether the road route is shielded or not after each row of anchor points identifies the road route on the image. Under the condition that the road line on the image is determined to be shielded, enlarging the receptive field of the pre-trained semantic segmentation model to determine the coordinate information of the shielded road line; performing polynomial fitting according to the coordinate information of the shielded road line to obtain a fitted curve of the lane line; displaying the shielded road line on the image according to the fitted curve of the lane line to obtain a complete road line; smoothing the complete road line according to the front frame image and the rear frame image of the image; determining whether the vehicle is pressed according to the contour information and the smoothed complete road line; and tracking the vehicle under the condition of the vehicle line pressing, and determining whether the vehicle has abnormal traffic behaviors.
According to the embodiment of the invention, the sense field of the semantic segmentation model is adjusted and enlarged to the whole graph, and the characteristics and information of other positions are required to be utilized, so that the convolutional network can fully learn and understand global context information. The image data collected by the camera are all sequences, the images have relevant continuity, the image of the previous frame can be used for predicting the image of the next frame to obtain a predicted road line, and the tracking prediction of the road line is realized. After predicting the pixel position of the occluded lane line (e.g., (leftx, lefty), (rightx, righty), and out _ img, where out _ img refers to the output image), then a polynomial fitting is performed on the left and right lane lines by a function to generate a fitting curve of x, y, i.e., the lane line for drawing, and the lane line fitting curve is rendered on the image to obtain the output image. After rendering the lane line fitting curve on the image, extracting each frame of image, filtering a large amount of interference information in the image, including image graying, filtering smoothing, image enhancement, binarization processing and edge repairing, and smoothing the lane line in the next frame of image by using the previous frame of image. After the blocked lane lines are displayed on the image, vehicles driving on the current road are identified, outline information of the vehicles driving on the current road (such as coordinates of the leftmost side and the rightmost side of the vehicle projected on the image) is determined, the outline information of the vehicles is compared with the coordinate information of the blocked lane lines, and whether abnormal traffic behaviors exist in the vehicles is determined, wherein the abnormal traffic behaviors comprise continuous line pressing behaviors and/or continuous line merging. In this embodiment, the camera is fixed, the vehicle is continuously moving, and when the vehicle is driving forward, the blocked lane line is continuously displayed to determine that the vehicle is continuously pressed, and if the vehicle is tracked to continuously contact with a plurality of lane lines in an offset manner, the vehicle is continuously offset.
According to the message reminding system provided by the embodiment of the invention, the camera is arranged at the high position of the current road, so that the system provided by the embodiment has the data acquisition capacity, the data (namely the image of the current road) acquired by the camera is identified through the edge calculation processing unit, whether abnormal traffic behaviors exist in the detection range is determined, if the abnormal traffic behaviors exist, the reminding message is generated and output, and therefore, the system provided by the embodiment has the abnormal traffic behavior detection capacity and the message transmission capacity; the vehicle-mounted unit is placed in a vehicle entering a current road (such as an expressway or an urban road), so that the vehicle has a technical means of receiving information, the capability of detecting abnormal traffic behaviors can be provided for the vehicle without automatic driving or driving assistance capability, the abnormal traffic behaviors of the vehicle can be accurately judged, the warning can be given to the line pressing lane changing of the vehicle, accidents such as rear-end collision and collision between the vehicle and surrounding vehicles can be prevented, the function of safe driving assistance is achieved, the risk of traffic accidents is reduced, and safer driving guarantee is provided. Fig. 6 schematically shows a structural schematic diagram of a message reminding system 600 according to another embodiment of the present invention, and as shown in fig. 6, the message reminding system 600 includes a camera 601, an edge calculation processing unit 602, an on-board unit 603, a road side unit 604 and a binding unit 605.
The binding unit 605 is configured to record an association relationship between the on-board unit and the vehicle when the on-board unit is placed in the vehicle entering the current road, so as to bind the on-board unit and the vehicle. In this embodiment, when a vehicle enters a current road, the on-board unit is obtained, and the binding unit records identification information (such as an ID) of the on-board unit and attribute information of the vehicle, such as a license plate number, so as to record an association relationship between the on-board unit and the vehicle.
The edge calculation processing unit 602 is further configured to: and under the condition that the abnormal traffic behavior of the vehicle running on the current road is determined, taking the vehicle with the abnormal traffic behavior as a target vehicle, and determining a target vehicle-mounted unit bound with the target vehicle according to the incidence relation recorded by the binding unit. Specifically, the edge calculation processing unit is further configured to: inquiring a preset content library, and determining reminding content corresponding to the abnormal traffic behavior of the target vehicle; determining attribute information of the target vehicle; determining the ID of a target vehicle-mounted unit placed in the target vehicle according to the attribute information of the target vehicle and the incidence relation recorded by the binding unit; generating a reminding message according to the reminding content and the ID of the target vehicle-mounted unit in the target vehicle;
the roadside unit 604 is further configured to: and sending the received reminding message to a target vehicle-mounted unit in the target vehicle. Specifically, the road side unit 604 is further configured to analyze the reminding message, and determine an ID and a reminding content of a target vehicle-mounted unit in the target vehicle; and sending the reminding content to a target vehicle-mounted unit in the target vehicle according to the ID of the target vehicle-mounted unit in the target vehicle.
According to the message reminding system provided by the embodiment of the invention, the association relationship between the vehicle and the vehicle-mounted unit is recorded through the binding unit, when the vehicle with the abnormal traffic behavior is detected, the vehicle-mounted unit corresponding to the vehicle with the abnormal traffic behavior is found according to the association relationship recorded by the binding unit, so that the reminding message can be sent to the corresponding vehicle, the capability of detecting the abnormal traffic behavior can be provided for the vehicle without automatic driving or auxiliary driving capability, the abnormal traffic behavior of the vehicle can be accurately judged, the early warning can be given to the line pressing and lane changing of the vehicle, the accidents of rear-end collision, collision and the like between the vehicle and the front vehicle can be prevented, the effect of safe auxiliary driving can be realized, the risk of traffic accidents is reduced, and the safer driving guarantee is provided.
The above-described solutions provided by the embodiments of the present invention may be implemented in hardware, in software modules running on one or more processors, or in a combination of them, in whole or in part. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in an electronic device according to embodiments of the present invention. Embodiments of the invention may also be implemented as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Programs that implement embodiments of the present invention may be stored on a computer-readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It is noted that, herein, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or step from another entity or step without necessarily requiring or implying any actual such relationship or order between such entities or steps. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a" \8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. A message reminding system is characterized by comprising a camera, an edge calculation processing unit and an on-board unit, wherein the on-board unit is placed in a vehicle when the vehicle enters a current road;
the camera is used for acquiring image data on the current road and sending the acquired image data to the edge calculation processing unit;
the edge calculation processing unit is used for analyzing the image data and identifying whether vehicles running on the current road have abnormal traffic behaviors or not; when the abnormal traffic behavior of the vehicle running on the current road is determined, generating a reminding message, and sending the reminding message to a vehicle-mounted unit in the vehicle with the abnormal traffic behavior;
the system also comprises a road side unit, and the edge calculation processing unit is also used for sending the reminding message to the road side unit;
the road side unit is used for sending the received reminding message to a vehicle-mounted unit in a vehicle with abnormal traffic behaviors;
the edge calculation processing unit is also used for analyzing the image data through a pre-trained semantic segmentation model and identifying whether vehicles running on the current road have abnormal traffic behaviors;
the edge calculation processing unit is further configured to:
analyzing the image data through the pre-trained semantic segmentation model, identifying a road route on the current road, and judging whether the road route is shielded; under the condition that the road line is determined to be occluded, determining coordinate information of the occluded road line; identifying a vehicle traveling on the current road, and determining profile information of the vehicle traveling on the current road; determining whether abnormal traffic behaviors exist in the vehicle according to the contour information and the coordinate information of the shielded road route, wherein the abnormal traffic behaviors comprise continuous line pressing behaviors and/or continuous line merging behaviors;
and the vehicle-mounted unit is used for outputting the reminding message after receiving the reminding message so as to remind a driver of the vehicle with abnormal traffic behaviors.
2. The system of claim 1, wherein the edge computation processing unit is further configured to:
for each frame of image in the image data, segmenting the image into line anchor frames through the pre-trained semantic segmentation model;
and identifying whether each line anchor point in the line anchor frame is a lane line or not so as to identify a lane line on the image.
3. The system of claim 2, wherein the edge computation processing unit is further configured to:
under the condition that the road line on the image is determined to be shielded, enlarging the receptive field of the pre-trained semantic segmentation model to determine the coordinate information of the shielded road line;
performing polynomial fitting according to the coordinate information of the shielded road line to obtain a fitted curve of the lane line;
displaying the shielded road line on the image according to the fitted curve of the lane line to obtain a complete road line;
smoothing the complete road line according to the front frame image and the rear frame image of the image;
determining whether the vehicle presses a line or not according to the contour information and the smoothed complete road line;
and tracking the vehicle under the condition of the vehicle line pressing, and determining whether the vehicle has abnormal traffic behaviors.
4. The system of claim 1, wherein the on-board unit comprises a voice announcement unit;
the voice broadcasting unit is used for broadcasting the reminding message.
5. The system of claim 1, further comprising a binding unit for recording an association relationship between the on-board unit and the vehicle when the on-board unit is put into the vehicle entering the current road to bind the on-board unit and the vehicle;
the edge calculation processing unit is further configured to: under the condition that the abnormal traffic behavior of the vehicles running on the current road is determined, the vehicles with the abnormal traffic behavior are taken as target vehicles, and the target vehicle-mounted unit bound with the target vehicles is determined according to the incidence relation recorded by the binding unit;
the roadside unit is further to: and sending the received reminding message to a target vehicle-mounted unit in the target vehicle.
6. The system of claim 5, wherein the binding unit is further configured to: recording the ID of the vehicle-mounted unit and the attribute information of the vehicle, and determining the association relationship between the vehicle-mounted unit and the vehicle so as to bind the vehicle-mounted unit and the vehicle;
the edge calculation processing unit is further configured to: inquiring a preset content library, and determining reminding content corresponding to the abnormal traffic behavior of the target vehicle; determining attribute information of the target vehicle; determining the ID of a target vehicle-mounted unit placed in the target vehicle according to the attribute information of the target vehicle and the incidence relation recorded by the binding unit; generating a reminding message according to the reminding content and the ID of the target vehicle-mounted unit in the target vehicle;
the roadside unit is further to: analyzing the reminding message, and determining the ID and the reminding content of the target vehicle-mounted unit in the target vehicle; and sending the reminding content to a target vehicle-mounted unit in the target vehicle according to the ID of the target vehicle-mounted unit in the target vehicle.
7. A message alert method, wherein the alert method is applied to the message alert system according to any one of claims 1 to 6; the method comprises the following steps:
acquiring image data on a current road through a camera, and sending the acquired image data to the edge calculation processing unit;
analyzing the image data through an edge computing processing unit, and identifying whether vehicles running on the current road have abnormal traffic behaviors; when the abnormal traffic behavior of the vehicle running on the current road is determined, generating a reminding message, and sending the reminding message to a vehicle-mounted unit in the vehicle with the abnormal traffic behavior;
the sending of the reminding message to the vehicle-mounted unit in the vehicle with abnormal traffic behaviors comprises the following steps:
sending the reminding message to the road side unit through the edge calculation processing unit;
sending the received reminding message to an on-board unit in a vehicle with abnormal traffic behaviors through the road side unit;
the analyzing the image data through the edge calculation processing unit to identify whether the vehicle running on the current road has abnormal traffic behaviors includes:
the edge calculation processing unit analyzes the image data through a pre-trained semantic segmentation model and identifies whether vehicles running on the current road have abnormal traffic behaviors;
the edge calculation processing unit analyzes the image data through a pre-trained semantic segmentation model, and identifies whether vehicles running on the current road have abnormal traffic behaviors, wherein the method comprises the following steps:
analyzing the image data through the pre-trained semantic segmentation model, identifying a road route on the current road, and judging whether the road route is shielded; determining coordinate information of the occluded road line in the case that it is determined that the road line is occluded; identifying a vehicle traveling on the current road, and determining profile information of the vehicle traveling on the current road; determining whether abnormal traffic behaviors exist in the vehicle or not according to the contour information and the coordinate information of the shielded road line, wherein the abnormal traffic behaviors comprise continuous line pressing behaviors and/or continuous line merging behaviors;
and outputting the reminding message through a vehicle-mounted unit so as to remind a driver of the vehicle with the abnormal traffic behavior.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111466524.6A CN114170798B (en) | 2021-12-03 | 2021-12-03 | Message reminding system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111466524.6A CN114170798B (en) | 2021-12-03 | 2021-12-03 | Message reminding system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114170798A CN114170798A (en) | 2022-03-11 |
| CN114170798B true CN114170798B (en) | 2023-02-17 |
Family
ID=80483128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111466524.6A Active CN114170798B (en) | 2021-12-03 | 2021-12-03 | Message reminding system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114170798B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115359440B (en) * | 2022-08-26 | 2024-01-12 | 武汉铁路职业技术学院 | Intelligent safe operation and system of railway locomotive based on Internet of things |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002312890A (en) * | 2001-04-09 | 2002-10-25 | Seiwa Electric Mfg Co Ltd | Method and system for calling attention to running vehicle |
| CN2938256Y (en) * | 2006-08-18 | 2007-08-22 | 高迟 | Prompting prealarm for vehicle turn-over line |
| CN108091142A (en) * | 2017-12-12 | 2018-05-29 | 公安部交通管理科学研究所 | For vehicle illegal activities Tracking Recognition under highway large scene and the method captured automatically |
| CN109949578A (en) * | 2018-12-31 | 2019-06-28 | 上海眼控科技股份有限公司 | A kind of illegal automatic auditing method of vehicle crimping based on deep learning |
| CN110867080A (en) * | 2019-12-05 | 2020-03-06 | 汪家琳 | Intelligent road system |
| CN113370992A (en) * | 2021-08-12 | 2021-09-10 | 天津所托瑞安汽车科技有限公司 | Vehicle line pressing reminding method and device and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000113396A (en) * | 1998-09-30 | 2000-04-21 | Nippon Signal Co Ltd:The | Support device for driving at intersection |
| CN102254429B (en) * | 2011-05-13 | 2013-07-10 | 东南大学 | Video identification-based detection method of detection device of violation vehicles |
| CN106412508A (en) * | 2016-09-30 | 2017-02-15 | 北京中星微电子有限公司 | Intelligent monitoring method and system of illegal line press of vehicles |
-
2021
- 2021-12-03 CN CN202111466524.6A patent/CN114170798B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002312890A (en) * | 2001-04-09 | 2002-10-25 | Seiwa Electric Mfg Co Ltd | Method and system for calling attention to running vehicle |
| CN2938256Y (en) * | 2006-08-18 | 2007-08-22 | 高迟 | Prompting prealarm for vehicle turn-over line |
| CN108091142A (en) * | 2017-12-12 | 2018-05-29 | 公安部交通管理科学研究所 | For vehicle illegal activities Tracking Recognition under highway large scene and the method captured automatically |
| CN109949578A (en) * | 2018-12-31 | 2019-06-28 | 上海眼控科技股份有限公司 | A kind of illegal automatic auditing method of vehicle crimping based on deep learning |
| CN110867080A (en) * | 2019-12-05 | 2020-03-06 | 汪家琳 | Intelligent road system |
| CN113370992A (en) * | 2021-08-12 | 2021-09-10 | 天津所托瑞安汽车科技有限公司 | Vehicle line pressing reminding method and device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 一种视频检测车辆位置违章的几何方法;严捷丰等;《小型微型计算机系统》;20090315(第03期);正文全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114170798A (en) | 2022-03-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8175331B2 (en) | Vehicle surroundings monitoring apparatus, method, and program | |
| US6442474B1 (en) | Vision-based method and apparatus for monitoring vehicular traffic events | |
| US7046822B1 (en) | Method of detecting objects within a wide range of a road vehicle | |
| CN110298300B (en) | Method for detecting vehicle illegal line pressing | |
| JP2020061079A (en) | Traffic violation vehicle identification system, server, and vehicle control program | |
| CN108932849B (en) | Method and device for recording low-speed running illegal behaviors of multiple motor vehicles | |
| CN113012436B (en) | Road monitoring method and device and electronic equipment | |
| CN101349562A (en) | Method and apparatus for alarming vehicle running bias direction | |
| CN113033275B (en) | Vehicle lane-changing non-turn signal lamp analysis system based on deep learning | |
| CN111145569A (en) | Road monitoring and vehicle running control method and device and vehicle-road cooperative system | |
| KR20100053318A (en) | A sensing system of a lane offense cars using the corner data and sensing method using the same | |
| CN111492416A (en) | Violation monitoring system and violation monitoring method | |
| CN105574502A (en) | Automatic detection method for violation behaviors of self-service card sender | |
| CN114170798B (en) | Message reminding system and method | |
| JP2994170B2 (en) | Vehicle periphery monitoring device | |
| CN111967451B (en) | Road congestion detection method and device | |
| CN112183206B (en) | Traffic participant positioning method and system based on road side monocular camera | |
| KR101418533B1 (en) | Vehicle Supervising Method | |
| CN113408319A (en) | Urban road abnormity perception processing method, device, system and storage medium | |
| CN115359443A (en) | Traffic accident detection method and device, electronic device and storage medium | |
| CN112542060B (en) | Rear side alarm device for vehicle | |
| JP2022056153A (en) | Temporary stop detection device, temporary stop detection system, and temporary stop detection program | |
| CN113112814A (en) | Snapshot method and device for no-stop right-turn vehicle and computer storage medium | |
| CN112597945A (en) | Vehicle detection method and device | |
| CN111696386A (en) | Lane line-based auxiliary early warning system, method and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |